Litcius/Paper detail

Pretrain-KGE: Learning Knowledge Representation from Pretrained Language Models

Zhiyuan Zhang, Xiaoqian Liu, Yi Zhang, Qi Su, Xu Sun, Bin He

202048 citationsDOIOpen Access PDF

Abstract

Conventional knowledge graph embedding (KGE) often suffers from limited knowledge representation, leading to performance degradation especially on the low-resource problem.

Topics & Concepts

Computer scienceEmbeddingRepresentation (politics)Resource (disambiguation)Artificial intelligenceNatural language processingKnowledge representation and reasoningPoliticsPolitical scienceComputer networkLawTopic ModelingNatural Language Processing TechniquesAdvanced Graph Neural Networks
Pretrain-KGE: Learning Knowledge Representation from Pretrained Language Models | Litcius